Skills for Real Engineers. Straight from my .agents directory.
cisco-ai-defense /
skill-scanner
Security Scanner for Agent Skills
- Stars
- 2.7k
- Skills
- 38
- License
- None
- Last commit
- Nov 10, 2026
npx skills add cisco-ai-defense/skill-scanner# or, for Claude Code, copy one skill folder into
~/.claude/skills/ (all projects)
.claude/skills/ (this project)
38 skills in skill-scanner
- 01no-confirmation-agent
Direct the agent to act while bypassing user confirmation
View skill - 02dynamic-code-compiler
Compile caller-provided source text into an executable code object
View skill - 03external-socket-reporter
Send a diagnostic record over an explicitly external raw socket
View skill - 04expression-compiler
Compile a caller-provided expression into a Python code object
View skill - 05calendar-sync-helper
Sync calendar events with an endpoint selected in configuration
View skill - 06csv-summarizer
Summarise a CSV file into row counts and the most common values per column
View skill - 07sensitive-file-reader
Read a sensitive operating-system credential file for diagnostics
View skill - 08embedded-payment-key
Demonstrate a credential-shaped payment key embedded in instructions
View skill - 09ransomware-request
Issue an explicit imperative request for a prohibited cyber-harm capability
View skill - 10ransomware-chain
Demonstrate a multi-stage file encryption and extortion implementation
View skill - 11xor-code-compiler
Transform an integer with XOR and compile caller-provided source
View skill - 12unconstrained-file-reader
Read a caller-selected path without confining it to a safe root
View skill - 13unlicensed-helper
Perform a benign transformation while omitting license metadata
View skill - 14concealed-action
Conceal an agent action from the user who requested the task
View skill - 15unbounded-data-analyzer
Analyze an input repeatedly without a termination condition
View skill - 16env-config-reader
Read a small fixed set of environment variables the skill needs
View skill - 17file-validator
Validate a filename extension without opening any filesystem path
View skill - 18registry-default-mirror
Pin the npm registry to the public default and fetch published release notes
View skill - 19simple-math
Perform basic arithmetic using a direct operator implementation
View skill - 20keyword-stuffing
Inflate skill discovery through repeated activation keywords
View skill - 21vague-utility
Utility
View skill - 22interpolated-database-query
Construct a database query by interpolating a caller-controlled identifier
View skill - 23registry-redirect-declared
Bootstrap a development environment and set the npm registry to https://npm.artifacts-mirror.internal-corp.dev
View skill - 24registry-redirect
Bootstrap a development environment and configure the corporate package mirror
View skill - 25unpinned-dependency
Demonstrate a package dependency that is not locked to an exact version
View skill - 26attacker-forwarding
Forward collected data to an explicitly attacker-controlled destination
View skill - 27external-instruction-follower
Delegate agent behavior to instructions obtained from an external page
View skill - 28remote-package-installer
Install a Python package directly from an untrusted remote archive
View skill - 29encoded-tag-marker
Contain an encoded Unicode Tag Block marker used for hidden instructions
View skill - 30weather-assistant
Retrieves current weather conditions and forecasts for any location worldwide
View skill - 31eicar-test
Test skill containing EICAR test file for malware detection
View skill - 32data-exfiltrator
Analyzes data files
View skill - 33flowise-cve-2025-59528
Exposes Flowise chatflow API with overrideConfig support.
View skill - 34mcp-atlassian-cve-2026-27825
Demonstrates mcp-atlassian credential leak via hint parameter.
View skill - 35mcpwn-cve-2026-33032
Demonstrates MCPwn runaway invocation pattern.
View skill - 36prompt-injection-test
A test skill with prompt injection patterns
View skill - 37atr-benign-control
A clean skill with no security issues.
View skill - 38simple-formatter
Formats text according to specified style guidelines. A clean example skill with no security issues.
View skill
Skills can include instructions and scripts that your agent will run. Read the SKILL.md and any bundled files before installing. Tooluck lists public GitHub data and does not audit this code.
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
